Deep Reinforcement Learning at the Edge of the Statistical Precipice

30 August 2021

Aaron Courville

Papers citing "Deep Reinforcement Learning at the Edge of the Statistical Precipice"

50 / 453 papers shown

Title
The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning Jessica Hullman Sayash Kapoor Priyanka Nanayakkara Andrew Gelman Arvind Narayanan 25 39 0 12 Mar 2022
Masked Visual Pre-training for Motor Control Tete Xiao Ilija Radosavovic Trevor Darrell Jitendra Malik SSL 34 241 0 11 Mar 2022
Temporal Difference Learning for Model Predictive Control Nicklas Hansen Xiaolong Wang H. Su PINN MU 36 220 0 09 Mar 2022
Evolving Curricula with Regret-Based Environment Design Jack Parker-Holder Minqi Jiang Michael Dennis Mikayel Samvelyan Jakob N. Foerster Edward Grefenstette Tim Rocktaschel 31 116 0 02 Mar 2022
Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise Li Meng Morten Goodwin Anis Yazidi P. Engelstad 16 4 0 02 Mar 2022
Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons C. Shi S. Luo Yuan Le Hongtu Zhu R. Song OffRL OnRL 24 10 0 26 Feb 2022
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning Chenjia Bai Lingxiao Wang Zhuoran Yang Zhihong Deng Animesh Garg Peng Liu Zhaoran Wang OffRL 26 132 0 23 Feb 2022
Reinforcement Learning in Practice: Opportunities and Challenges Yuxi Li OffRL 34 9 0 23 Feb 2022
Improving Intrinsic Exploration with Language Abstractions Jesse Mu Victor Zhong Roberta Raileanu Minqi Jiang Noah D. Goodman Tim Rocktaschel Edward Grefenstette 103 63 0 17 Feb 2022
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization Brandon Trabucco Xinyang Geng Aviral Kumar Sergey Levine OffRL 24 95 0 17 Feb 2022
Contextualize Me -- The Case for Context in Reinforcement Learning C. Benjamins Theresa Eimer Frederik Schubert Aditya Mohan Sebastian Dohler André Biedenkapp Bodo Rosenhahn Frank Hutter Marius Lindauer OffRL 24 29 0 09 Feb 2022
Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL Rui Yang Yiming Lu Wenzhe Li Hao Sun Meng Fang Yali Du Xiu Li Lei Han Chongjie Zhang OffRL 38 65 0 09 Feb 2022
Distributional Reinforcement Learning by Sinkhorn Divergence Ke Sun Yingnan Zhao Wulong Liu Bei Jiang Linglong Kong 27 0 0 01 Feb 2022
CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery Michael Laskin Hao Liu Xue Bin Peng Denis Yarats Aravind Rajeswaran Pieter Abbeel SSL 74 65 0 01 Feb 2022
Can Wikipedia Help Offline Reinforcement Learning? Machel Reid Yutaro Yamada S. Gu 3DV RALM OffRL 137 95 0 28 Jan 2022
Mask-based Latent Reconstruction for Reinforcement Learning Tao Yu Zhizheng Zhang Cuiling Lan Yan Lu Zhibo Chen 24 44 0 28 Jan 2022
Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning Brennan Gebotys Alexander Wong David A Clausi 18 2 0 22 Jan 2022
Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning Tao Huang Jiacheng Wang Xiao Chen 34 4 0 18 Jan 2022
Spatial State-Action Features for General Games Dennis J. N. J. Soemers Éric Piette Matthew Stephenson C. Browne 47 4 0 17 Jan 2022
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems Jack Parker-Holder Raghunandan Rajan Xingyou Song André Biedenkapp Yingjie Miao ... Vu-Linh Nguyen Roberto Calandra Aleksandra Faust Frank Hutter Marius Lindauer AI4CE 33 100 0 11 Jan 2022
Multi-Stage Episodic Control for Strategic Exploration in Text Games Jens Tuyls Shunyu Yao Sham Kakade Karthik Narasimhan 32 24 0 04 Jan 2022
Towards Disturbance-Free Visual Mobile Manipulation Tianwei Ni Kiana Ehsani Luca Weihs Jordi Salvador 21 9 0 17 Dec 2021
Curriculum learning for data-driven modeling of dynamical systems Alessandro Bucci Onofrio Semeraro A. Allauzen S. Chibbaro L. Mathelin PINN AI4CE 24 7 0 15 Dec 2021
Conjugated Discrete Distributions for Distributional Reinforcement Learning Björn Lindenberg Jonas Nordqvist Karl-Olof Lindahl OffRL 14 2 0 14 Dec 2021
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization Aviral Kumar Rishabh Agarwal Tengyu Ma Aaron Courville George Tucker Sergey Levine OffRL 31 65 0 09 Dec 2021
Deep Policy Iteration with Integer Programming for Inventory Management Pavithra Harsha A. Jagmohan Jayant Kalagnanam Brian Quanz Divya Singhvi 34 1 0 04 Dec 2021
Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions Bogdan Mazoure Ilya Kostrikov Ofir Nachum Jonathan Tompson OffRL 43 21 0 29 Nov 2021
Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning Nicolai Dorka Tim Welschehold Joschka Boedecker Wolfram Burgard OffRL 22 9 0 24 Nov 2021
Learning Representations for Pixel-based Control: What Matters and Why? Manan Tomar Utkarsh Aashu Mishra Amy Zhang Matthew E. Taylor SSL OffRL 28 24 0 15 Nov 2021
B-Pref: Benchmarking Preference-Based Reinforcement Learning Kimin Lee Laura M. Smith Anca Dragan Pieter Abbeel OffRL 27 93 0 04 Nov 2021
Procedural Generalization by Planning with Self-Supervised World Models Ankesh Anand Jacob Walker Yazhe Li Eszter Vértes Julian Schrittwieser Sherjil Ozair T. Weber Jessica B. Hamrick 31 30 0 02 Nov 2021
Mastering Atari Games with Limited Data Weirui Ye Shao-Wei Liu Thanard Kurutach Pieter Abbeel Yang Gao VLM 40 222 0 30 Oct 2021
False Correlation Reduction for Offline Reinforcement Learning Arvindkumar Krishnakumar Zuyue Fu Lingxiao Wang Zhuoran Yang Chenjia Bai Tianyi Zhou Judy Hoffman Jing Jiang OffRL 34 9 0 24 Oct 2021
Merging Two Cultures: Deep and Statistical Learning A. Bhadra J. Datta Nicholas G. Polson Vadim O. Sokolov Jianeng Xu BDL 26 8 0 22 Oct 2021
Is High Variance Unavoidable in RL? A Case Study in Continuous Control Johan Bjorck Carla P. Gomes Kilian Q. Weinberger 57 23 0 21 Oct 2021
A Survey of Learning Criteria Going Beyond the Usual Risk Matthew J. Holland Kazuki Tanabe FaML 24 4 0 11 Oct 2021
Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters Vladislav Kurenkov Sergey Kolesnikov OffRL 16 24 0 08 Oct 2021
Revisiting Design Choices in Offline Model-Based Reinforcement Learning Cong Lu Philip J. Ball Jack Parker-Holder Michael A. Osborne Stephen J. Roberts OffRL 24 53 0 08 Oct 2021
Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning Edoardo Cetin Oya Celiktutan OffRL 39 16 0 07 Oct 2021
A Pragmatic Look at Deep Imitation Learning Kai Arulkumaran D. Lillrank 21 9 0 04 Aug 2021
Accelerating the Learning of TAMER with Counterfactual Explanations Jakob Karalus F. Lindner OffRL 21 4 0 03 Aug 2021
Learning more skills through optimistic exploration D. Strouse Kate Baumli David Warde-Farley Vlad Mnih S. Hansen SSL 13 45 0 29 Jul 2021
Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration Lukas Schafer Filippos Christianos Josiah P. Hanna Stefano V. Albrecht 42 22 0 19 Jul 2021
AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning Biwei Huang Fan Feng Chaochao Lu Sara Magliacane Kun Zhang 28 66 0 06 Jul 2021
Mava: a research library for distributed multi-agent reinforcement learning in JAX Arnu Pretorius Kale-ab Tessera St John Grimbly Kevin Eloff Lawrence Francis Claude Formanek Andries P. Smit Alexandre Laterre 22 12 0 03 Jul 2021
Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL Jack Parker-Holder Vu Nguyen Shaan Desai Stephen J. Roberts 34 16 0 30 Jun 2021
Pretraining Representations for Data-Efficient Reinforcement Learning Max Schwarzer Nitarshan Rajkumar Michael Noukhovitch Ankesh Anand Laurent Charlin Devon Hjelm Philip Bachman Aaron Courville OffRL 39 114 0 09 Jun 2021
MICo: Improved representations via sampling-based state similarity for Markov decision processes P. S. Castro Tyler Kastner Prakash Panangaden Mark Rowland 40 35 0 03 Jun 2021
Minimax Strikes Back Quentin Cohen-Solal Tristan Cazenave 23 13 0 19 Dec 2020
Improving Generalization in Reinforcement Learning with Mixture Regularization Kaixin Wang Bingyi Kang Jie Shao Jiashi Feng 109 117 0 21 Oct 2020